Quantifying Visual Image Quality: A Bayesian View

TL;DR

This paper reviews image quality assessment models from a Bayesian perspective, aiming to unify various approaches and explore their implications for biological and artificial vision systems.

Contribution

It introduces a Bayesian framework to unify diverse IQA methods and discusses their relevance to vision science and practical applications.

Findings

Bayesian approach unifies multiple IQA models

Insights into biological vision influence IQA design

Discussion on limitations and future prospects

Abstract

Image quality assessment (IQA) models aim to establish a quantitative relationship between visual images and their perceptual quality by human observers. IQA modeling plays a special bridging role between vision science and engineering practice, both as a test-bed for vision theories and computational biovision models, and as a powerful tool that could potentially make profound impact on a broad range of image processing, computer vision, and computer graphics applications, for design, optimization, and evaluation purposes. IQA research has enjoyed an accelerated growth in the past two decades. Here we present an overview of IQA methods from a Bayesian perspective, with the goals of unifying a wide spectrum of IQA approaches under a common framework and providing useful references to fundamental concepts accessible to vision scientists and image processing practitioners. We discuss the implications of the successes and limitations of modern IQA methods for biological vision and the prospect for vision science to inform the design of future artificial vision systems.